用可解释的沟通优化建议，提升远程医疗反馈率
Improving Medical Communication using Rubric-Guided Counterfactual Recommendations
- 基于大模型生成反事实建议，优化语气、个性化等沟通特征
- 平均提升6.41%正面反馈概率，93.31%建议不降低反馈
- 适合医生快速改进沟通，保持医疗内容不变
基于文本的远程医疗越来越依赖轻量级患者反馈，但此类反馈主要反映沟通质量而非医学准确性。我们提出一种由语言模型引导的反事实推荐流程，无需干扰医疗内容即可发现并优化语气、个性化、行动力和问题覆盖度等可解释的沟通特征。这些特征结合医患交互元数据用于预测正面反馈。推理时，系统搜索低成本有序特征变化，推荐能提升正面反馈概率的最小化沟通调整，并通过独立审计模型验证其泛化能力。在多轮交互中，推荐使预测正面反馈概率平均提升6.41%，且93.31%的建议不产生负向影响。结果表明，微小且可解释的沟通调整可捕获大部分增益，同时保留医生对医学推理和最终措辞的控制权。
原文摘要 · Abstract (English)
Text-based telemedicine increasingly relies on lightweight patient feedback, however, such feedback primarily reflects perceived communication quality rather than medical accuracy. We introduce an LM-guided counterfactual recommendation pipeline that discovers and refines interpretable communication features such as tone, personalization, actionability and completeness in addressing patient concerns, without interfering with the medical content. These features are used together with patient-doctor interaction metadata to estimate positive feedback. At inference time, the system searches over low-cost ordinal feature changes and recommends minimal communication changes predicted to increase the probability of positive feedback, while independent auditor models test whether these gains generalize beyond the selection model. Across interactions, recommendations yield a mean +6.41% gain in predicted positive feedback probability under independent auditors, and are non-negative for 93.31% of recommendations. These results suggest that small, interpretable communication changes can capture most predicted gains while preserving the doctor's control over medical reasoning and final wording.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。